PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks

被引:64
|
作者
Mandal, Kalikinkar [1 ]
Gong, Guang [1 ]
机构
[1] Univ Waterloo, Waterloo, ON, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Privacy-preserving computation; Predictive analysis; Federated learning; Machine learning;
D O I
10.1145/3338466.3358926
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Federated Learning (FL) enables a large number of users to jointly learn a shared machine learning (ML) model, coordinated by a centralized server, where the data is distributed across multiple devices. This approach enables the server or users to train and learn an ML model using gradient descent, while keeping all the training data on users' devices. We consider training an ML model over a mobile network where user dropout is a common phenomenon. Although federated learning was aimed at reducing data privacy risks, the ML model privacy has not received much attention. In this work, we present PrivFL, a privacy-preserving system for training (predictive) linear and logistic regression models and oblivious predictions in the federated setting, while guaranteeing data and model privacy as well as ensuring robustness to users dropping out in the network. We design two privacy-preserving protocols for training linear and logistic regression models based on an additive homomorphic encryption (HE) scheme and an aggregation protocol. Exploiting the training algorithm of federated learning, at the core of our training protocols is a secure multiparty global gradient computation on alive users' data. We analyze the security of our training protocols against semi-honest adversaries. As long as the aggregation protocol is secure under the aggregation privacy game and the additive HE scheme is semantically secure, PrivFL guarantees the users' data privacy against the server, and the server's regression model privacy against the users. We demonstrate the performance of PrivFL on real-world datasets and show its applicability in the federated learning system.
引用
收藏
页码:57 / 68
页数:12
相关论文
共 50 条
  • [31] Federated Learning for Privacy-Preserving Machine Learning in IoT Networks
    Anitha, G.
    Jegatheesan, A.
    2024 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT CYBER PHYSICAL SYSTEMS AND INTERNET OF THINGS, ICOICI 2024, 2024, : 338 - 342
  • [32] Towards Privacy-Preserving Location Sharing over Mobile Online Social Networks
    Chen, Juan
    Su, Shen
    Wang, Xianzhi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2019, E102D (01) : 133 - 146
  • [33] Making Privacy-preserving Federated Graph Analytics Practical (for Certain Queries)
    Liu, Kunlong
    Gupta, Trinabh
    PROCEEDINGS OF THE 29TH ACM SYMPOSIUM ON ACCESS CONTROL MODELS AND TECHNOLOGIES, SACMAT 2024, 2024, : 31 - 39
  • [34] CryptoFE: Practical and Privacy-Preserving Federated Learning via Functional Encryption
    Qian, Xinyuan
    Li, Hongwei
    Hao, Meng
    Yuan, Shuai
    Zhang, Xilin
    Guo, Song
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 2999 - 3004
  • [35] A Privacy Preserving Similarity Search Scheme over Encrypted High-Dimensional Data for Multiple Data Owners
    Guo, Cheng
    Tian, Pengxu
    Jie, Yingmo
    Tang, Xinyu
    CLOUD COMPUTING AND SECURITY, PT II, 2018, 11064 : 484 - 495
  • [36] Practical Privacy-Preserving Friend Recommendations on Social Networks
    Brendel, William
    Han, Fangqiu
    Marujo, Luis
    Jie, Luo
    Korolova, Aleksandra
    COMPANION PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2018 (WWW 2018), 2018, : 111 - 112
  • [37] Blockchain-Based Privacy-Preserving Federated Learning for Mobile Crowdsourcing
    Ma, Haiying
    Huang, Shuanglong
    Guo, Jiale
    Lam, Kwok-Yan
    Yang, Tianling
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (08): : 13884 - 13899
  • [38] A Privacy-preserving Data Alignment Framework for Vertical Federated Learning
    Gao, Ying
    Xie, Yuxin
    Deng, Huanghao
    Zhu, Zukun
    Zhang, Yiyu
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2024, 46 (08): : 3419 - 3427
  • [39] CROWDFL: Privacy-Preserving Mobile Crowdsensing System Via Federated Learning
    Zhao, Bowen
    Liu, Ximeng
    Chen, Wei-Neng
    Deng, Robert H.
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2023, 22 (08) : 4607 - 4619
  • [40] CrowdFA: A Privacy-Preserving Mobile Crowdsensing Paradigm via Federated Analytics
    Zhao, Bowen
    Li, Xiaoguo
    Liu, Ximeng
    Pei, Qingqi
    Li, Yingjiu
    Deng, Robert H.
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 : 5416 - 5430